sast-missingauth

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data in the form of source code from various projects. This creates an attack surface where a malicious codebase could contain hidden instructions within comments, string literals, or metadata intended to override the agent's behavior, skip detections, or produce false negatives.
  • Ingestion points: The subagents ingest route definitions, middleware implementations, and controller logic from the local file system (SKILL.md, Phase 1 and Phase 2).
  • Boundary markers: The instructions do not provide explicit delimiters or "ignore embedded instructions" warnings for the subagents when they are processing the target source code.
  • Capability inventory: The skill possesses the capability to read arbitrary project files, spawn multiple subagents in parallel, and write summary findings to the file system.
  • Sanitization: There is no evidence of content sanitization, filtering, or escaping applied to the source code snippets before they are presented to the LLM for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:34 AM
Security Audit — agent-trust-hub — sast-missingauth